© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11428
    Prev
    Next
    INDEX
    Explanations

    Crohn's disease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atham
    -0.20
    笺
    -0.19
    çİ°æľī
    -0.18
    UV
    -0.18
    ores
    -0.18
    /values
    -0.17
    Ñīий
    -0.17
    æ±Ĥ
    -0.17
    agini
    -0.17
    èIJ½åľ¨
    -0.17
    POSITIVE LOGITS
     Wich
    0.20
    ctl
    0.19
    ungan
    0.18
    mag
    0.18
    ugo
    0.18
    possibly
    0.18
    itty
    0.18
    ç©¿è¶Ĭ
    0.18
     mag
    0.18
    æĥĨ
    0.17
    Activations Density 0.005%

    No Known Activations